What Are the Common Metrics for Evaluating Model Performance?
Several metrics are commonly used to evaluate model performance in epidemiology:
1. Sensitivity and Specificity: Sensitivity measures the model's ability to identify true positives (actual cases), while specificity measures its ability to identify true negatives (non-cases).
2. Predictive Values: Positive predictive value (PPV) and negative predictive value (NPV) indicate the probability that subjects identified by the model as positive or negative are correctly classified.
3. ROC Curve and AUC: The Receiver Operating Characteristic (ROC) curve and the Area Under the Curve (AUC) provide insights into the trade-offs between sensitivity and specificity and overall model performance.
4. Mean Squared Error (MSE) and Root Mean Squared Error (RMSE): These metrics are used for continuous outcome models to measure the average squared difference between observed and predicted values.
